| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.015384171610434315, |
| "eval_steps": 500, |
| "global_step": 100, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0015384171610434315, |
| "grad_norm": 28460.13671875, |
| "learning_rate": 1.9999999999999996e-07, |
| "loss": 7.6905, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.003076834322086863, |
| "grad_norm": 1011.0682373046875, |
| "learning_rate": 1.2e-06, |
| "loss": 7.3827, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.004615251483130294, |
| "grad_norm": 1202.7293701171875, |
| "learning_rate": 2.1999999999999997e-06, |
| "loss": 6.9075, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.006153668644173726, |
| "grad_norm": 1114.82568359375, |
| "learning_rate": 3.1999999999999994e-06, |
| "loss": 6.7876, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.007692085805217157, |
| "grad_norm": 316.300048828125, |
| "learning_rate": 4.2e-06, |
| "loss": 6.702, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.009230502966260589, |
| "grad_norm": 1428.5538330078125, |
| "learning_rate": 5.199999999999999e-06, |
| "loss": 6.5171, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.01076892012730402, |
| "grad_norm": 554.1876220703125, |
| "learning_rate": 6.199999999999999e-06, |
| "loss": 6.5737, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.012307337288347452, |
| "grad_norm": 696.2239990234375, |
| "learning_rate": 7.2e-06, |
| "loss": 6.5013, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.013845754449390882, |
| "grad_norm": 987.22607421875, |
| "learning_rate": 8.2e-06, |
| "loss": 6.3895, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.015384171610434315, |
| "grad_norm": 96.93306732177734, |
| "learning_rate": 9.199999999999998e-06, |
| "loss": 6.3879, |
| "step": 100 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 100000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 16, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1964612513218560.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
